Active Learning for Hyperspectral Image Classification via Hypergraph Neural Network

In recent years, deep neural networks have been widely used for hyperspectral image (HSI) classification and have shown excellent performance using numerous labeled samples. The acquisition of HSI labels is usually based on the field investigation, which is expensive and time consuming. Hence, the available labels are usually limited, which affects the efficiency of deep HSI classification methods. To improve the classification performance while reducing the labeling cost, this article proposes a semisupervised deep learning (DL) method for HSI classification, named pyramidal dilation attention convolutional network with active and self-paced learning (PDAC-ASPL), which integrates active learning (AL), self-paced learning (SPL), and DL into a unified framework. First, a densely connected pyramidal dilation attention convolutional network is trained with a limited number of labeled samples. Then, the most informative samples from the unlabeled set are selected by AL and queried real labels, and the highest confidence samples with corresponding pseudo labels are extracted by SPL. Finally, the samples from AL and SPL are added to the training set to retrain the network. Compared with some DL- and AL-based HSI classification methods, our PDAC-ASPL achieves better performance on four HSI datasets.

In recent years, graph convolutional networks (GCNs) have gained increasing attention in hyperspectral image (HSI) classification due to their good ability to model the pairwise relationships between two pixels. However, it is difficult to effectively model more complex relationships among multiple pixels with simple graphs. To solve this problem, we propose a novel tensorized high-order hypergraph convolutional network (TH<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>GCN) for HSI classification. Specifically, the hypergraph structure is employed to effectively model complex spatial relationships between pixels in HSIs, and we propose a new tensor-based algebraic representation of hypergraphs as a powerful strategy for describing the high-order interaction structures of the hypergraph. Besides, by extending the adjacency matrix-based GCN to the tensor domain and exploiting the tensor decomposition, the TH<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>GCN method is designed to efficiently extract high-order discriminative information from the hypergraph at low complexity for improving HSI classification performance. Furthermore, the construction of the adjacency tensor on all the data requires a huge amount of memory, especially for large-scale remote sensing images. To this end, the TH<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>GCN is trained and tested for HSI data in a minibatch fashion. Experimental results on three HSI datasets prove that the performance of the proposed method outperforms the comparison methods.

Deep learning has achieved great success in hyperspectral image (HSI) classification. However, its success relies on the availability of sufficient training samples. Unfortunately, the collection of training samples is expensive, time-consuming, and even impossible in some cases. Natural image datasets that are different from HSI, such as Image Net and mini-ImageNet, have abundant texture and structure information. Effective knowledge transfer between two heterogeneous datasets can significantly improve the accuracy of HSI classification. In this letter, heterogeneous few-shot learning (HFSL) for HSI classification is proposed with only a few labeled samples per class. First, few-shot learning is performed on the mini-ImageNet datasets to learn the transferable knowledge. Then, to make full use of the spatial and spectral information, a spectral&#x2013;spatial fusion network is devised. Spectral information is obtained by the residual network with pure 1-D operators. Spatial information is extracted by a convolution network with pure 2-D operators, and the weights of the spatial network are initialized by the weights of the model trained on the mini-ImageNet datasets. Finally, few-shot learning is fine-tuned on HSI to extract discriminative spectral&#x2013;spatial features and individual knowledge, which can improve the classification performance of the new classification task. Experiments conducted on two public HSI datasets demonstrate that the HFSL outperforms the existing few-shot learning methods and supervised learning methods for HSI classification with only a few labeled samples. Our source code is available at <uri>https://github.com/Li-ZK/HFSL</uri>.

Hyperspectral image (HSI) classification, due to its characteristic combination of images and spectra, has important applications in various fields through pixel-level image classification. The fusion of spatial–spectral features is a topic of great interest in the context of hyperspectral image classification, which typically requires selecting a larger spatial neighborhood window, potentially leading to overlaps between training and testing samples. Vision Transformer (ViTs), with their powerful global modeling abilities, have had a significant impact in the field of computer vision through various variants. In this study, an ensemble learning framework for HSI classification is proposed by integrating multiple variants of ViTs, achieving high-precision pixel-level classification. Firstly, the spatial shuffle operation was introduced to preprocess the training samples for HSI classification. By randomly shuffling operations using smaller spatial neighborhood windows, a greater potential spatial distribution of pixels can be described. Then, the training samples were transformed from a 3D cube to a 2D image, and a learning framework was built by integrating seven ViT variants. Finally, a two-level ensemble strategy was employed to achieve pixel-level classification based on the results of multiple ViT variants. Our experimental results demonstrate that the proposed ensemble learning framework achieves stable and significantly high classification accuracy on multiple publicly available HSI datasets. The proposed method also shows notable classification performance with varying numbers of training samples. Moreover, herein, it is proven that the spatial shuffle operation plays a crucial role in improving classification accuracy. By introducing superior individual classifiers, the proposed ensemble framework is expected to achieve even better classification performance.

The application of graph convolutional networks (GCN) in hyperspectral image (HSI) classification has become a promising method, thanks to its flexible convolution operation in any irregular image region. For the classification of HSI, GCN can extract more superpixel-level features with a topological structure, in comparison to the traditional convolutional neural networks (CNNs) using fixed square kernels distilling pixel-level features. To fully leverage the different levels of features, this study proposes a novel deep network referred to as a CNN-combined graph residual network ( C 2 GRN), which integrates the multilevel graph residual module and spectral-spatial features continuous learning module. During the extraction of topology information using the former module, HSI pixels are divided into superpixels and served as input nodes of the module to reduce the computational complexity and obtain the multilevel spatial relevance between adjacent superpixels. Besides, for the latter module, the spectral-spatial features are learnt continuously, which could obtain the finer pixel-level features. Finally, the captured spectral-spatial features of different levels are concatenated. This strategy could not only adequately utilize the correlation and difference of adjacent spatial but also obtain the finer and more valuable spectral-spatial information, which makes a significant boost in the HSI classification. Additionally, the experiment results demonstrate the superiority and availability of the C 2 GRN on three benchmark datasets of HSI, compared with the state-of-the-art methods for the classification of HSI.

Graph convolutional networks (GCNs) have garnered extensive attention in the realm of hyperspectral image (HSI) classification. However, due to the problem of over-smoothing caused by deep GCN, most of the existing GCN-based methods are limited to constructing shallow networks, thus only able to extract superficial features. Moreover, when existing shallow GCNs extend to a more deeper structure, the number of learnable parameters increase linearly, thus leading to poor generalization performance under limited training samples. To address the aforementioned issues, a Separable Deep Graph Convolutional Network Integrated with CNN and Prototype Learning (SDGCP) is proposed for HSI classification, which can extract effective global structural information of HSI without increasing the number of trainable parameters. Specifically, the spectral and spatial features, adaptively selected by the attention module, are encoded into the structure of a graph by the graph encoder with the assistance of the pixel-to-region mapping obtained from the simple linear iterative clustering (SLIC). Then, a separable deep graph convolution module, composed of feature extraction and deep feature propagation, is adopted to capture the long-range contextual relationships from HSI encoded as graph data, which is combined with locally complementary information extracted by CNN after decoding. Finally, to further boost the performance of classification under limited labeled samples, prototype learning with regularization terms is utilized to enhance the intra-class compactness and inter-class separability of feature representations. Extensive experiments on three standard HSI data sets demonstrate the superiority of the proposed SDGCP over the state-of-the-art (SOTA) methods.

Graph convolutional networks (GCNs) are a promising approach for addressing the necessity for long-range information in hyperspectral image (HSI) classification. Researchers have attempted to develop classification methods that combine strong generalizations with effective classification. However, the current HSI classification methods based on GCN present two main challenges. First, they overlook the multi-view features inherent in HSIs, whereas multi-view information interacts with each other to facilitate classification tasks. Second, many algorithms perform a rudimentary fusion of extracted features, which can result in information redundancy and conflicts. To address these challenges and exploit the strengths of multiple features, this paper introduces an adaptive multi-feature fusion GCN (AMF-GCN) for HSI classification. Initially, the AMF-GCN algorithm extracts spectral and textural features from the HSIs and combines them to create fusion features. Subsequently, these three features are employed to construct separate images, which are then processed individually using multi-branch GCNs. The AMG-GCN aggregates node information and utilizes an attention-based feature fusion method to selectively incorporate valuable features. We evaluated the model on three widely used HSI datasets, i.e., Pavia University, Salinas, and Houston-2013, and achieved accuracies of 97.45%, 98.03%, and 93.02%, respectively. Extensive experimental results show that the classification performance of the AMF-GCN on benchmark HSI datasets is comparable to those of state-of-the-art methods.

Hyperspectral image (HSI) classification faces challenges in diverse scenarios due to spectral-spatial complexity and class imbalance. Existing methods lack generalizability. This paper presents a novel Graph-Convolutional Networks with Adaptive Region Ensembles (GCN-ARE) framework. It integrates graph spectral learning, dynamic region subdivision, and classifier fusion. The key contributions are as follows: First, a normalized graph Laplacian operator ensures graph spectral stability, bounding the eigenvalue spectrum to stabilize feature propagation and address gradient issues in irregular terrains. Second, recursive K-means clustering under empirical risk bounds achieves adaptive region optimality, dynamically partitioning complex regions for enhanced local discriminability. Third, theoretical guarantees based on Hoeffding’s inequality enable dynamic ensemble consistency, facilitating optimal classifier selection under spatial-spectral uncertainty. Experiments on four HSI datasets (Botswana, Houston, Indian Pines, WHU-Hi-LongKou) show that GCN-ARE outperforms benchmarks like ViT and GAT, with average OA improvements of 1.5–5.7%. Ablation studies confirm the importance of adaptive subdivision and ensemble modules, and parameter sensitivity analyses reveal its robustness. The framework sets a new standard for robust HSI classification with its theoretical rigor and practical efficacy.

Deep convolutional neural networks (CNNs) have shown their outstanding performance in the hyperspectral image (HSI) classification. The success of CNN-based HSI classification relies on the availability sufficient training samples. However, the collection of training samples is expensive and time consuming. Besides, there are many pretrained models on large-scale data sets, which extract the general and discriminative features. The proper reusage of low-level and midlevel representations will significantly improve the HSI classification accuracy. The large-scale ImageNet data set has three channels, but HSI contains hundreds of channels. Therefore, there are several difficulties to simply adapt the pretrained models for the classification of HSIs. In this article, heterogeneous transfer learning for HSI classification is proposed. First, a mapping layer is used to handle the issue of having different numbers of channels. Then, the model architectures and weights of the CNN trained on the ImageNet data sets are used to initialize the model and weights of the HSI classification network. Finally, a well-designed neural network is used to perform the HSI classification task. Furthermore, attention mechanism is used to adjust the feature maps due to the difference between the heterogeneous data sets. Moreover, controlled random sampling is used as another training sample selection method to test the effectiveness of the proposed methods. Experimental results on four popular hyperspectral data sets with two training sample selection strategies show that the transferred CNN obtains better classification accuracy than that of state-of-the-art methods. In addition, the idea of heterogeneous transfer learning may open a new window for further research.

Hyperspectral image (HSI) classification is the subject of intense research in remote sensing. The tremendous success of deep learning in computer vision has recently sparked the interest in applying deep learning in hyperspectral image classification. However, most deep learning methods for hyperspectral image classification are based on convolutional neural networks (CNN). Those methods require heavy GPU memory resources and run time. Recently, another deep learning model, the transformer, has been applied for image recognition, and the study result demonstrates the great potential of the transformer network for computer vision tasks. In this paper, we propose a model for hyperspectral image classification based on the transformer, which is widely used in natural language processing. Besides, we believe we are the first to combine the metric learning and the transformer model in hyperspectral image classification. Moreover, to improve the model classification performance when the available training samples are limited, we use the 1-D convolution and Mish activation function. The experimental results on three widely used hyperspectral image data sets demonstrate the proposed model’s advantages in accuracy, GPU memory cost, and running time.

With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual labeling. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research directions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related techniques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://github.com/ShuGuoJ/HSI-Classification.git.

We study self-taught learning for hyperspectral image (HSI) classification with small labeled and unlabeled data sets. Supervised deep learning methods are currently state of the art for many machine learning problems, but these methods require large quantities of labeled data to be effective. Unfortunately, existing labeled HSI benchmarks are too small to train a deep supervised network. Alternatively, self-taught learning methods use sufficiently large quantities unlabeled data to improve the performance on a given image classification task. However, the unlabeled HSI data is also difficult to obtain. To overcome this limitation, we employ an online dictionary learning algorithm for sparse coding to self-taught learning, in which we extract features from much smaller unlabeled data sets. Furthermore, apart from the spectral information we also apply the spatial information to improve the performance of classification. Our results convinced that the proposed approach can extract discriminative features from small unlabeled and labeled data sets for classification. In addition, the results obtained by our approach are better than the results obtained by principal component analysis (PCA).

In hyperspectral image (HSI) classification task, semisupervised graph convolutional network (GCN)-based methods have received increasing attention. However, two problems still need to be addressed. The first is that the initial graph structure in the GCN-based methods is not sufficiently flexible to encode the homogenous structure similarity of HSI pixels when facing the complex scenarios induced by the spatial variability. Another problem is that the input (graph structure) and output (output features) of the GCN-based methods are separated with a ``single pass'' procedure, which is a suboptimal problem for HSI classification because it does not flexibly optimize the graph construction with a feedback method via output features. In this article, a novel spatial-spectral unified adaptive probability GCN (SSAPGCN) method is proposed for HSI classification. First, considering the homogeneous structural similarity of the pairwise relationships of HSI pixels, this article combines the inherent spectral information and spatial coordinates to obtain the spatial-spectral adaptive probability graph (SSAPG) structure, which can capture the probabilistic connectivity between each pair of the homogeneous HSI pixels. Second, the SSAPG structure and GCN model are combined into a unified framework to a daptively learn both the graph structure and the output features simultaneously with feedback. Finally, the proposed SSAPGCN method with two layers is evaluated on four public HSI datasets to demonstrate its superiority over different classification methods in terms of two evaluation metrics, the overall accuracy (OA) and kappa coefficient (KC), especially with small training sample sizes.

The performance of hyperspectral image (HSI) classification relies on the pixel information obtained from hundreds of contiguous and narrow spectral bands. Existing approaches, however, are limited to exploit an appropriate latent subspace for data representation within the pixel-level or superpixel-level. To utilize spectral information and spatial correlation among pixels in HSI and avoid the “salt-and-pepper” problem generated in the pixel-based HSI classification, a novel pixel-level and superpixel-level aware subspace learning method called PSASL is developed. The PSASL constructs the subspace learning framework based on the reconstruction independent component analysis algorithm. The spectral–spatial graph regularization and label space regularization are developed as the pixel-level constraints. To avoid the “salt-and-pepper” problem generated in the pixel-based classification methods, superpixel-level constraints are introduced for integrating the data representations defined in the subspace and class probabilities of the pixels in the same superpixel. The subspace learning and the pixel-level regularization are combined with the superpixel-level regularization to form a unified objective function. The solution to the objective function is efficiently achieved by employing a customized iterative algorithm, and it converges very fast. A discriminative data representation and a universal multiclass classifier are learned simultaneously. We test the PSASL on three widely used HSI data sets. Experimental results demonstrate the superior performance of our method over many recently proposed methods in HSI classification.

Hyperspectral image (HSI) classification is a current research hotspot. Most existing methods usually export discriminative features with low-quality distribution and low information utilization, which may induce classification performance degeneration. To remedy such deficiencies, we propose a diagonalized low-rank learning (DLRL) model for HSI classification in this study. Specifically, a classwise regularization is used to capture the classwise block-diagonal structure of low-rank representation, which can further cluster the represented HSI pixels from one class into the same subspace and extract features with well-ordered distribution. Such a regularization assists to easily and correctly classify HSIs. In addition, we combine sparsity and collaboration to extract more discriminative features for guaranteeing high information utilization, i.e., a tradeoff of sparsity and collaboration is sought to acquire both correlations among HSI pixels and characteristics of each pixel. By this way, rich information in the HSI can be fully used for good feature extraction. Further, the estimated feature representation is used as an input to the support vector machine (SVM) classifier for HSI classification. Extensive experiments have been done to validate that the proposed DLRL method achieves much classification performance in contrast to several state-of-the-art algorithms.